AI Paper Atlas

Research map / Label-efficient and robust learning / Zero-/few-shot and meta-learning

Few-Shot Learning With a Strong Teacher

Han-Jia Ye, Ming Lu, De‐Chuan Zhan, Wei‐Lun Chao

TPAMI 2022 · Label-efficient and robust learning › Zero-/few-shot and meta-learning · approach: Meta-learning analysis and benchmarks · 86 citations (OpenAlex)

Read the paperCheck your idea against 137,217 papers

AI-extracted. The measured effects below were read by AI from the paper's full text (no summary yet). Numbers and claims can be wrong or missing context, so check the paper before you cite or build on it.

Measured effects reported in the paper

What was changedWhereMeasuredEffect
add LastShot (NC) teacher supervisionProtoNet · miniImageNet 1-shotaccuracy: 62.39 -> 64.16Improved
add LastShot (NC)FEAT · miniImageNet 1-shotaccuracy: 66.78 -> 67.33Improved
add LastShot (LR)MetaOptNet · miniImageNet 1-shotaccuracy: 63.21 -> 65.08Improved
add LastShot (NC)FEAT · tieredImageNet 1-shotaccuracy: 71.13 -> 72.03Improved
add LastShot (LR)FEAT · FC-100 1-shotaccuracy: 42.56 -> 44.08Improved
add LastShot (LR)FEAT · miniImageNet 50-shotaccuracy: 87.83 -> 89.03Improved
use B-class base classifier as teacher (ablation)FEAT · miniImageNet 1-shotaccuracy: 66.78 -> 66.89No clear effect
weaken student with Autoaug without LastShot (ablation)FEAT · miniImageNet 1-shotaccuracy: 66.78 -> 65.22Hurt
enlarge teacher inputs instead of direct query (ablation)FEAT + LastShot (NC) · miniImageNet 1-shotaccuracy: 66.97 -> 67.33Improved
ensemble with SimpleShot instead of LastShot (ablation)FEAT · miniImageNet 5-shotaccuracy: 82.05 -> 81.76No clear effect
add LastShot (NC) over ensemble (ablation)ProtoNet · miniImageNet 5-shotaccuracy: 81.10 -> 81.23Improved
increase lambda to 10 (ablation)FEAT + LastShot (NC) · miniImageNet 50-shotaccuracy: 88.76 -> 87.34Hurt

Earlier methods this paper compares with

Named baselines from earlier accepted papers in this paper's results tables: better than 1 of 1 on most shared results.

Matched by method name in results tables read by AI. Authors' own tables tend to favour the newer method, and a comparison can be missed when a method is renamed.

Closest papers by meaning

Writing a paper in this area? scime draft is a free LaTeX editor with AI included, real-time co-authors and a check of your references and venue rules before you submit. It also imports OpenAI Prism projects.

Open scime draft

Get the next scime Dispatch and a monthly field update

Free. We send a confirmation link first; every email has a one-click unsubscribe. Privacy